adroll
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the @membranehq/cli package, which is the official tool provided by the vendor for platform interaction.\n- [COMMAND_EXECUTION]: The skill uses the membrane command-line interface to execute various integration tasks, including authentication, connection management, and running API actions.\n- [PROMPT_INJECTION]: The skill processes external data from AdRoll and interprets user intents to dynamically find or generate actions. This creates a surface for indirect prompt injection where data from external APIs could potentially influence agent behavior.
Audit Metadata